Improved README with a Quick Start, Dataset Setup and Project Usage G…

README.md

@@ -1,5 +1,18 @@
 ![ML4Sci x DeepLense](/Images_for_README/DEEPLENSE.png)
 
+## 🚀 Quick Start
+
+Follow these steps to set up the project quickly:
+
+```bash
+git clone https://github.com/ML4SCI/DeepLense.git
+cd DeepLense
+
+python -m venv venv
+source venv/bin/activate   # Windows: venv\Scripts\activate
+
+pip install -r requirements.txt
+
 ## 1. Background
 
 We at DeepLense explore cutting-edge Machine Learning techniques for the study of Strong Gravitational Lensing and Dark Matter Sub-structure. We use both simulated and real lensing images, for a variety of tasks, using a variety of techniques.
@@ -26,6 +39,45 @@ In DeepLense, we’re mainly dealing with three kinds of simulated Dark Matter:
 
 ## 2. Datasets
 
+## 2.1 Dataset Setup
+
+To run the models in this repository, you need to download and
+properly organize the datasets.
+
+### 📥 Download
+
+Datasets can be generated or downloaded from:
+https://github.com/mwt5345/DeepLenseSim
+
+(Refer to the repository for instructions specific to each dataset.)
+
+### 📁 Directory Structure
+
+After downloading, organize the dataset as follows:
+DeepLense/
+│── data/
+│   ├── model_1/
+│   ├── model_2/
+│   ├── model_3/
+│   └── model_4/
+│
+│── scripts/
+│── models/
+│── README.md
+
+### ⚙️ Preprocessing
+
+- Ensure images are in the expected format (e.g., `.npy`, `.png`)
+- Normalize or preprocess data if required by specific scripts
+- Check individual project folders for custom preprocessing steps
+
+### ▶️ Running Training
+
+Example:
+
+```bash
+python train.py --data_path ./data/model_1
+
 All datasets are constructed using Lenstronomy, by Michael W. Toomey, as presented in their [repository](https://github.com/mwt5345/DeepLenseSim/tree/main/).
 
 | Dataset | Lens model | Light Profile | Modelling strategy |
@@ -35,11 +87,76 @@ All datasets are constructed using Lenstronomy, by Michael W. Toomey, as present
 |Model 3 dataset|Sheared Isothermal Elliptical lens | Sérsic light profile | HST's observation characteristics, Axion DM and CDM substructure appended to base halo to create 3 sub-structure classes
 |Model 4 dataset|Two Isothermal Elliptical lenses | Three-channel **real galaxy** images | Euclid's observation characteristics, Axion DM and CDM substructure appended to base halo to create 3 sub-structure classes
 
+---
+
+## 📦 Dataset Setup
+
+This project uses simulated gravitational lensing datasets generated using Lenstronomy.
+
+### 1. Download / Generate Dataset
+
+Datasets can be generated using the official simulation repository:
+
+https://github.com/mwt5345/DeepLenseSim/tree/main/
+
+Follow the instructions in that repository to generate datasets corresponding to:
+- Model 1
+- Model 2
+- Model 3
+- Model 4
+
+*(If pre-generated datasets are available, they can be linked here in the future.)*
+
+---
+
+### 2. Directory Structure
+
+After downloading or generating the dataset, organize it as follows:
+DeepLense/
+│── data/
+│   └── dataset_name/
+│       ├── train/
+│       ├── test/
+│       └── labels/
+
+---
+
+### 3. Configure Dataset Path
+
+Ensure the dataset path is correctly set in the training scripts. For example:
+
+```python
+data_dir = "./data/dataset_name/"
+
 ## 3. Projects
 
+This section contains various research and implementation projects developed under DeepLense, primarily through GSoC contributions. Each project focuses on different machine learning approaches applied to gravitational lensing datasets.
+
+👉 Navigate to individual project folders for code, training scripts, and detailed instructions.
+
+
 ![Project compositions](/Images_for_README/DeepLense%20project%20composition.jpeg)
 ![Techniques compositions](/Images_for_README/DeepLense%20ML%20Techniques.jpeg)
 
+---
+
+### 🧭 How to Use These Projects
+
+1. Choose a project from the table below  
+2. Navigate to its repository folder  
+3. Check for:
+   - `train.py` or `main.py`
+   - notebooks (`.ipynb`)
+   - specific README (if available)
+
+4. Run the project using:
+
+```bash
+python train.py
+```
+
+⚠️ Note: Each project may have different dependencies and dataset requirements.
+
 | Project Name | Contributor | Task | ML Techniques | Repository Link | Blog Post |
 |---|---|---|---|---|---|
 |[DeepLense Classification Using Vision Transformers](#311-deeplense-classification-using-vision-transformers)|Archil Srivastava|Sub-structure classification|Vision Transformer Variants|[Click Here](https://github.com/ML4SCI/DeepLense/tree/main/DeepLense_Classification_Transformers_Archil_Srivastava)|[Click Here](https://medium.com/@archilsrivastava/transformers-for-dark-matter-morphology-with-strong-gravitational-lensing-gsoc-2022-with-ml4sci-b34a03d30114)|